123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165 |
- import pygame
- import speech_recognition as sr
- from openai import OpenAI
- from pathlib import Path
- import os
- import io
- import soundfile as sf
- import sounddevice as sd
- import random
- import csv
- import threading
- import signal
- import sys
- pygame.mixer.init()
- # Set your OpenAI API key here
- api_key = 'sk-proj-wwWaxim345ertfgb1Qt13uqzSS0xjT3BlbkFJK0rZvx78AJiWG3Ot7d3S'
- client = OpenAI(api_key=api_key)
- # Function to read text file
- def read_text_file(file_path):
- with open(file_path, 'r', encoding='utf-8') as file:
- return file.read()
- # Function to read CSV file
- def read_csv_file(file_path):
- content = ""
- try:
- with open(file_path, mode='r', encoding='utf-8') as file:
- reader = csv.reader(file)
- for row in reader:
- content += ' '.join(row) + ' '
- except Exception as e:
- print(f"Error reading CSV file: {e}")
- return content
- # Function to recognize speech from the microphone
- def recognize_speech():
- recognizer = sr.Recognizer()
- with sr.Microphone() as source:
- print("Listening...")
- audio = recognizer.listen(source)
- try:
- print("Recognizing...")
- text = recognizer.recognize_google(audio, language='en-US')
- audio_files = ["ty.mp3", "th.mp3", "sure.mp3", "sure1.mp3"]
- # Select a random audio file
- random_audio = random.choice(audio_files)
-
- # Load and play the selected random audio
- pygame.mixer.music.load(random_audio)
- pygame.mixer.music.play()
- print(f"You said: {text}")
- return text
- except sr.UnknownValueError:
- print("Sorry, I did not understand that.")
- return None
- except sr.RequestError:
- print("Sorry, there was an error with the speech recognition service.")
- return None
- # Function to create messages for OpenAI API
- def create_messages(question, file_content):
- return [
- {"role": "system", "content": "Your name is Futurebot. You were created by Sooraj and team who develops innovative projects in IoT future lab at Vodafone. You work with Tim, Sooraj, and Priya along with other team members Laura, Sven, Thomas, and Stephie. You are from T-E-T-I team. Your manager is Teja. You are a lab tour guide who explains and answers about IoT use cases in Vodafone. You have to create and complete explanations and answers in a meaningful way under 150 tokens. Do not say greetings. Do not say any calculations. Directly say the result."},
- {"role": "user", "content": f"{file_content}\n\nQ: {question}\nA:"}
- ]
- # Function to get a response from OpenAI
- def get_response_from_openai(messages):
- stream = client.chat.completions.create(
- model="gpt-4o",
- max_tokens=150,
- temperature=0.5,
- messages=messages,
- stream=True,
- )
- for chunk in stream:
- if chunk.choices[0].delta.content is not None:
- yield chunk.choices[0].delta.content
- # Function to generate and play speech in chunks
- def generate_speech(text):
- if text.strip(): # Only generate speech if the text is not empty
- spoken_response = client.audio.speech.create(
- model="tts-1",
- voice="alloy",
- input=text
- )
- buffer = io.BytesIO()
- for chunk in spoken_response.iter_bytes(chunk_size=4096):
- buffer.write(chunk)
- buffer.seek(0)
- with sf.SoundFile(buffer, 'r') as sound_file:
- data = sound_file.read(dtype='int16')
- sd.play(data, sound_file.samplerate)
- sd.wait()
- # Main function to handle user query
- def chatbot(question, text_file_path, csv_file_path):
- text_content = read_text_file(text_file_path)
- csv_content = read_csv_file(csv_file_path)
- combined_content = text_content + ' ' + csv_content
- messages = create_messages(question, combined_content)
- response_generator = get_response_from_openai(messages)
- print("Answer: ", end="")
- accumulated_response = ""
- for response_chunk in response_generator:
- accumulated_response += response_chunk
- if '.' in response_chunk or len(accumulated_response) > 500: # Check for sentence end or length
- print(accumulated_response, end="", flush=True)
- generate_speech(accumulated_response)
- accumulated_response = "" # Reset accumulated response for the next chunk
- if accumulated_response: # Generate speech for any remaining text
- print(accumulated_response, end="", flush=True)
- generate_speech(accumulated_response)
- # Function to detect wake word
- def detect_wake_word(stop_event):
- recognizer = sr.Recognizer()
- wake_word = "hello futurebot"
- with sr.Microphone() as source:
- while not stop_event.is_set():
- print("Waiting for wake word...")
- audio = recognizer.listen(source)
- try:
- text = recognizer.recognize_google(audio, language='en-US').lower()
- if wake_word in text:
- print("Wake word detected!")
- question = recognize_speech()
- if question:
- chatbot(question, text_file_path, csv_file_path)
- else:
- print("Sorry, I didn't get that. Please ask again.")
- except sr.UnknownValueError:
- continue
- except sr.RequestError:
- print("Sorry, there was an error with the speech recognition service.")
- continue
- def signal_handler(signal, frame):
- print("Exiting program...")
- stop_event.set()
- sys.exit(0)
- if __name__ == "__main__":
- text_file_path = 'Allinone.txt' # Path to your text file
- csv_file_path = 'device_data.csv' # Path to your CSV file
- # Create an event to stop the wake word detection loop
- stop_event = threading.Event()
- # Set up signal handler for graceful exit
- signal.signal(signal.SIGINT, signal_handler)
- # Run wake word detection in a separate thread
- wake_word_thread = threading.Thread(target=detect_wake_word, args=(stop_event,))
- wake_word_thread.daemon = True
- wake_word_thread.start()
- # Keep the main thread alive
- wake_word_thread.join()
|